Neural Network training using the Extended Kalman Filter

A function using the extended Kalman filter to train MLP neural networks

Description

The extended Kalman filter can not only estimate states of nonlinear dynamic systems from noisy measurements but also can be used to estimate parameters of a nonlinear system. A direct application of parameter estimation is to train artificial neural networks. This function and an embeded example shows a way how this can be done.

Acknowledgements

Learning The Extended Kalman Filter inspired this file.

This file inspired Neural Network Training Using The Unscented Kalman Filter.

• MATLAB release: MATLAB 7.5 (R2007b)
• Other requirements: It requires the ekf function, which can be downloaded from the following link: http://www.mathworks.com/matlabcentral/fileexchange/loadFile.do?objectId=18189&objectType=FILE

[SaiNave]

I have suffered this kind of error using this file

Maximum recursion limit of 500 reached. Use set(0,'RecursionLimit',N) to change the
limit. Be aware that exceeding your available stack space can crash MATLAB and/or your
computer.

Error in nnekf

[Kalyan]

good

[luo]

good jod

[luo]

good

[Daniel]

For newer versions of matlab, it's recommended to use:

rng('default')
rng('shuffle')

instead of:

rand('state', 0)

[Dinie Muhammad]

Great job!

[V. Poor]

 

[x y]

Great job!

[Devanathan M]

Very nice

[piyush singhal]

it is a good effort pl generate codes for it which can be help ful for mpc

[a s]

 

[lekouch khalid]

is an intersent work

[mahendra shukla]

too good